為了在 GPS 拒絕區域內實現對多個全向型移動機器人（ODMR）之跟隨控制的無線導航，設計了用於跟隨控制的自適應遞迴神經網路之有限時間控制（ARNN-FTC）和用於ODMR無線導航的殘差之雙向長短期記憶（RBLSTM）模型。ARNN-FTC的優點是殘差遞迴神經網路可以補償每個 ODMR的總動態之不確定性，且與以前的研究相比，新參考姿態的設計也減少了所需的輸入功率。此外，RBLSTM與Bi-LSTM模型相比，RBLSTM的優點在可以保持其梯度信號，以便分佈式模組的超寬頻網路（DM-UWBN）更有效地學習。由於ARNN-FTC（取樣時間5ms）、WiFi通信（30ms）和 DM-UWBN（150ms）為多重取樣率的任務，相應的導航及跟隨控制將面臨更大的挑戰。最終，實現了具有單向和雙向通信的多個 ODMR 之無線導航和跟隨控制，以驗證所提出方法的有效性和實用性。

To accomplish the wireless navigation for the following control of multiple omnidirectional mobile robots (ODMRs) in the global GPS-denied region, the proposed adaptive RNN-based finite-time control (ARNN-FTC) for following control and Residual Bi-LSTM (RBLSTM) model for wireless navigation of ODMRS are designed. The advantageous features of ARNN-FTC are the residual RNN to compensate total dynamic uncertainties of each ODMR and a new design of reference pose to attenuate the input power in comparison to previous studies. In addition, the beneficent advantageous characteristic of RBLSTM is to maintain its gradient signal for a more effective learning of distributive module UWB network (DM-UWBN) in comparison to Bi-LSTM model. Due to multi-sampling tasks of ARNN-FTC (e.g., 5ms), WiFi communication (30ms), and DM-UWBN (e.g., 150ms), the corresponding navigation and following control multiple ODMRs will be more challenged. Moreover, their unidirectional and bidirectional communications are implemented and compared to validate the effectiveness and practicality of the proposed approach.

參考文獻
[1] K. Zinchenko, C.-Y. Wu, K.-T. Song, “A study on speech recognition control for a surgical robot,” IEEE Trans. Ind. Inform., vol. 14, no. 2, pp. 607-617, Mar. 2017.
[2] C.-F Juang, C.-H. Lin, and T. B. Bui, “Multiobjective rule-based cooperative continuous ant colony optimized fuzzy systems with a robot control application,” IEEE Trans. Cybern., vol. 50, no. 2, pp.650-663, Feb. 2020.
[3] V. Mwaffo, P. DeLellis, and J. S. Humbert, “Formation control of stochastic multivehicle systems,” IEEE Trans. Contr. Syst. Technol., vol. 29, no. 6, pp. 2505-2516, Nov. 2021.
[4] S. Zhou, Z. Miao, H. Zhao, Z. Liu, H. Wang, and Y.-H. Liu, “Vision-based control of an industrial vehicle in unstructured environments,” IEEE Trans. Contr. Syst. Technol., DOI: 10. 1109/TCST.2021.3073003.
[5] Y. Zhu, J. Wu, and H. Su, “V2V-based cooperative control of uncertain, disturbed and constrained nonlinear CAVs platoon,” IEEE Trans. Intell. Transp. Syst., DOI: 10.1109/ TITS.2020.3026877.
[6] C.-F. Juang, C.-Y. Chou, and C.-T. Lin, “Navigation of a fuzzy- controlled wheeled robot through the combination of expert knowledge and data-driven multiobjective evolutionary learning,” IEEE Trans. Cybern., DOI: 10.1109/TCYB.2020.3041269.
[7] M. Gheisarnejad and H. M. Khooban, “An intelligent non-integer PID controller-based deep reinforcement learning: implementation and experimental results,” IEEE Trans. Ind. Electron., vol. 68, no. 4, pp. 3609-3618, Apr. 2021.
[8] C.-L. Hwang, “Comparison of path tracking control of a car-like mobile robot with and without motor dynamics,” IEEE/ASME Trans. Mechatronics, vol. 21, no. 4, pp. 1801- 1811, Aug. 2016.
[9] C.-H. G. Li, L.-P. Zhou, and Y.-H. Chao, “Self-balancing two- wheeled robot featuring intelligent end-to-end deep visual- steering,” IEEE Trans. Mechatronics, vol. 26, no. 5, pp. 2263-2273, Oct. 2021.
[10] J. Wang, X. Luo, J. Yan, and X. Guan, “Distributed integrated sliding mode control for vehicle platoons based on disturbance observer and multi power reaching law,” IEEE Trans. Intell. Transp. Syst., DOI: 10.1109/TITS.2020. 3035764.
[11] T. Terakawa, M. Komori, K. Matsuda, and S. Mikami, “A novel omnidirectional mobile robot with wheels connected by passive sliding joints,” IEEE/ASME Trans. Mechatronics, vol. 23, no. 4, 1716-1727, Jul. 2018.
[12] C. Ren, X. Li , X. Yang, and S. Ma, “Extended state observer-based sliding mode control of an omnidirectional mobile robot with friction compensation,” IEEE Trans. Ind. Electron., vol. 66, no. 12, pp. 9480-9489, Dec. 2019.
[13] C.-L. Hwang, D.-S. Wang, F.-C. Weng, and S.-L. Lai, “Interactions between specific human and omnidirectional mobile robot using deep learning approach: SSD-FN-KCF,” IEEE Access, vol. 8, pp. 41186- 41200, 2020.
[14] C.-L. Hwang, F. C. Weng, D. S. Wang, and F. Wu, “Experimental validation of speech improvement based adaptive stratified finite-time saturation control of omnidirectional service robot,” IEEE Trans. Sys., Man, Cybern.: Syst., vol. 52, no. 2, pp. 1317-1330, Feb. 2022.
[15] D. Li, W. Zhang, W. He, C. Li, and S. S. Ge, “Two-layer distributed formation-containment control of multiple Euler–Lagrange systems by output feedback,” IEEE Trans. Cybern., vol. 49, no. 2, pp. 675-687, Feb. 2019.
[16] L. Liu, D. Wang, Z. Peng, T. Li, and C. L. P. Chen, “Cooperative path following ring-networked under-actuated autonomous surface vehicles: algorithms and experimental results,” IEEE Trans. Cybern., vol. 50, no. 4, pp.1509-1519, Apr. 2020.
[17] C. Yu, X. Xiang, P. A. Wilson, and Q. Zhang, “Guidance-error-based robust fuzzy adaptive control for bottom following of a flight-style AUV with saturated actuator dynamics,” IEEE Trans. Cybern., vol. 50, no. 5, pp. 1887-1899, May 2020.
[18] B. Ning, Q.-L. Han, and Q. Lu, “Fixed-time leader-following consensus for multiple wheeled mobile robots,” IEEE Trans. Cybern., vol. 50, no. 10, pp.4381-4392, Oct. 2020.
[19] J. Ni and P. Shi, “Adaptive neural network fixed-time leader–follower consensus for multiagent systems with constraints and disturbances,” IEEE Trans. Cybern., vol. 51, no. 4, pp. 1835-1848, Apr. 2021.
[20] C. Song, Y. Fan, and S. Xu, “Finite-time coverage control for multiagent systems with unidirectional motion on a closed curve,” IEEE Trans. Cybern., vol. 51, no. 6, pp. 3071-3078, Jun. 2021.
[21] K. Li, C. Hua, X. You, and X. Guan, “Distributed output-feedback consensus control for nonlinear multiagent systems subject to unknown input delays,” IEEE Trans. Cybern., vol. 52, no. 2, pp. 1292-1301, Feb. 2022.
[22] S.-L. Dai, K. Lu, and J. Fu, “Adaptive finite-time tracking control of nonholonomic multirobot formation systems with limited field- of-view sensors,” IEEE Trans. Cybern., DOI: 10.1109/TCYB.2021. 3063481.
[23] W. Xiao, H. Ren, Q. Zhou, H. Li, and R. Lu, “Distributed finite-time containment control for nonlinear multiagent systems with mismatched disturbances,” IEEE Trans. Cybern., DOI: 10.1109/TCYB.2020.3042168.
[24] X. Zhao, Q. Zong, B. Tian, and M. You, “Finite-time dynamic allocation and control in multiagent coordination for target tracking,” IEEE Trans. Cybern., DOI:10.1109/TCYB. 2021.3063481.
[25] B. Cui, Y. Xia, K. Liu, J. Zhang, Y. Wang, and G. Shen, “Truly distributed finite-time attitude formation-containment control for networked uncertain rigid spacecraft,” IEEE Trans. Cybern., DOI: 10. 1109/TCYB. 2020.3034645.
[26] X. Li, Z. Xu, S. Li, Z. Su, and X. Zhou, “Simultaneous obstacle avoidance and target tracking of multiple wheeled mobile robots with certified safety,” IEEE Trans. Cybern., DOI: 10.1109/TCYB.2021.3070385.
[27] Zuo, J. Song, and Q.-L. Han, “Coordinated planar path-following control for multiple nonholonomic wheeled mobile robots,” IEEE Trans. Cybern., DOI:10.1109/TCYB. 2021.3057335.
[28] S. Dai, Z. Wu, J. Wang, M. Tan, and J. Yu, “Barrier-based adaptive line-of-sight 3-D path-following system for a multijoint robotic fish with sideslip compensation,” IEEE Trans. Cybern., DOI: /10.1109/ TCYB.2022.3155761.
[29] J. Zhao, X. Li, X. Yu, and H. Wang, “Finite-time cooperative control for bearing-defined leader-following formation of multiple double- integrators,” IEEE Trans. Cybern., DOI: 10.1109/TCYB. 2021. 3124827.
[30] Y. Xu, J. Sun, Z.-G. Wu, and G. Wang, “Fully distributed adaptive event-triggered control of networked systems with actuator bias faults,” IEEE Trans. Cybern., DOI:10.1109/ TCYB.2021.3059049.
[31] X.-G. Guo, W.-D. Xu, J.-L. Wang, J. H. Park, and H. Yan, “BLF-based neuroadaptive fault-tolerant control for nonlinear vehicular platoon with time-varying fault directions and distance restrictions,” IEEE Trans. Intell. Transp. Syst., DOI: 10.1109/ TITS.2021.3113928.
[32] C.-L. Hwang and H. B. Abebe, “Generalized and heterogeneous nonlinear dynamic multiagent systems using online RNN-based finite-time formation tracking control and application to transportation systems,” IEEE Trans. Intell. Transp. Syst., DOI: 10.1109/TITS. 2021.3126662.
[33] K. Guo, X. Li, and L. Xie, “Ultra-wideband and odometry-based cooperative relative localization with application to multi-UAV formation control,” IEEE Trans. Cybern., vol. 50, no. 6, pp. 2590-2603, Jun. 2020.
[34] K. He, X. Zhang, S. Ren, and J. Sun, “Identity mappings in deep residual networks,” in arXiv:1603.05027v3, Jul 2016.
[35] G. Yang and H. Xu, “A residual BiLSTM model for named entity recognition,” IEEE Access, vol. 8, pp. 227710-227718, 2020.
[36] M.-S. Ko, K. Lee, J.-K. Kim, C. W. Hong, Z. Y. Dong, and K. Hur, “Deep concatenated residual network with bidirectional LSTM for one-hour-ahead wind power forecasting,” IEEE Trans. Sustainable Energy, vol. 12, no. 2, pp. 1321-1335, Apr. 2021.
[37] H. K. Khalil, Noninear System. 2nd Ed., Prentice-Hall Inc. 1996.
[38] S. R. Dubey, S. Chakraborty, S. K. Roy, S. Mukherjee, S. K. Singh, and B. B. Chaudhuri, “diffGrad: An optimization method for convolutional neural networks,” IEEE Trans. Neural Netw. Learn. Syst., vol. 31, no. 11, pp. 4500-4511, Nov. 2020.